large language models

Open White Paper on Geophysical Computing: Ubiquitous Decentralized Computing Bus and Multi-Track Decoupled Dynamo Architecture (Project Amanda, Version 2.2)

This white paper presents Project Amanda (Version 2.2), a novel decentralized neuromorphic hardware architecture designed to break through the constraints of conventional deterministic computing paradigms. Conventional neuromorphic computing relies excessively on cost-prohibitive pre-hardware perceptual training and cu...

Portfolio Optimization with Covariance from News-Derived Information Networks

Intercompany relationships change over time, but they are difficult to incorporate into traditional return-based covariance estimates. This article proposes a practical three-step framework for transforming financial news into a covariance input for portfolio optimization. First, a large language model extracts dynamic...

Understanding On-Screen Text Do AI Tools Struggle with Hawaiian Chyrons?

Metadata describing legacy television broadcasts in archival collections is often incomplete or inconsistent, but additional information about the program content and contributors can be recovered from on-screen text. Leveraging this information requires text extraction, and the accuracy of this process is crucial for...

MridAI: Autonomous Edge-to-Conversational IoT for Democratising Precision Agriculture via Neuro-Symbolic Telemetry

While sensor-guided precision agriculture improves water efficiency and curtails chemical run-off, adoption across smallholder farm land in the Global South remains under 1%. Commercial telemetry systems are constrained by high capital acquisition costs (>$300) and complex, dashboard-centric mobile applications that im...

Large Language Model-Enhanced Multi-Agent Reinforcement Learning for Autonomous Enterprise Workflow Orchestration via Graph Semantic Routing

# LeMARLA **Large Language Model-Enhanced Multi-Agent Reinforcement Learning for Autonomous Enterprise Workflow Orchestration via Graph Semantic Routing.** LeMARLA couples an LLM-driven task decomposition module, a heterogeneous graph attention routing module over tasks, employees and skills, and a CTDE multi-agent rei...

EuLLM — Open-source sovereign LLM platform

EuLLM is an open-source platform for creating, distributing, and running sovereign EU-compliant Large Language Models, designed for verticalization across domains, languages, and brands while ensuring AI Act compliance. The platform consists of three components: Engine — a Rust-based inference runtime built on top of l...

Data poisoning in LLM multiagent societies: Social proof drives collective decision failure in financial deliberation

Large language model (LLM) multiagent systems are increasingly deployed for high‐stakes financial deliberation, but individually secure LLMs may become vulnerable when embedded in a peer‐to‐peer agent society. We study data poisoning in such societies using Moltbook, a deliberation test bed modeled after the agent‐on...

ToshLLM: local LLM inference on Intel Macs with AMD GPUs

A native SwiftUI application that runs large language models locally on Intel Macs with AMD GPUs, a configuration mainstream inference stacks leave unsupported or incorrect. Beyond packaging, it contributes original work to the Metal backend of llama.cpp: ToshGEMM, a manually tiled matrix multiply that replaces the sim...

Generative Artificial Intelligence and Large Language Models as Methodological Support Tools in Health Research: A Bibliometric Analysis

Semantic-Conditioned Spectral Fusion for Label-Efficient Multispectral Adaptation of Frozen Remote-Sensing Vision–Language Models

Remote-sensing vision–language models (RS-VLMs) yield transferable, text-alignable representations, yet are pre-trained on three-band RGB imagery and therefore cannot exploit the red-edge, near-infrared and short-wave-infrared bands that carry much of the discriminative signal in multispectral data. Existing adaptation...

Semantic Spacetime, Semantic Gravity, and the Law of Attention

A Framework for Meaning Mass, Contextual Curvature, Attention Allocation, and Evolvable Semantic Systems Description This work develops an integrated theoretical framework for understanding how meaning, attention, and context interact across cognitive, artificial, cultural, and civilizational systems. The framework com...

An Availability-Oriented, Multi-Provider Architecture for Generative AI Services: A Fault-Injection Case Study

Applications built on third-party Generative AI APIs inherit the unreliability of those APIs. Providers rate-limit requests, exhaust free-tier quotas, deprecate models, and return server errors, any of which can break a dependent application. This paper presents an availability-oriented architecture that does not depen...